memovai/mimiclaw

MimiClaw: Harness on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 29 minutes ago
Added to GitGenius on September 11th, 2026
Created on February 4th, 2026
Open Issues & Pull Requests: 111 (+0)
GitHub issues: Enabled
Number of forks: 890
Total Stargazers: 5,746 (+0)
Total Subscribers: 53 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 54
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 185 days
Stale 30+ days: 54
Stale 90+ days: 53

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • enhancement (30)
  • bug (16)
  • question (14)
  • P2 (3)
  • documentation (3)
  • P0 (2)
  • P1 (1)
  • P3 (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

MimiClaw is an edge AI assistant that runs on a $5 ESP32-S3 microcontroller with no operating system, requiring only pure C and USB power.

The tool solves the problem of deploying AI agents to extremely resource-constrained hardware by implementing a lightweight agent loop entirely in C. It connects to Telegram for user interaction, integrates with either Anthropic Claude or OpenAI GPT as the language model provider, and maintains local memory on the device's flash storage so the assistant learns and remembers across reboots. The system operates on minimal power consumption and requires only WiFi connectivity to function.

MimiClaw suits developers building always-on personal AI assistants, IoT applications, or edge deployments where traditional server infrastructure is impractical or unnecessary. It is designed for those who want a self-contained, locally-controlled AI agent without the overhead of Linux, Node.js, or cloud dependencies. The project targets makers and embedded systems developers comfortable with microcontroller development and the ESP32 ecosystem.

Almost all open issues are raised by outside users rather than the core team, indicating a substantial base of adopters reporting real-world use. Maintainers typically respond to new issues and pull requests within a day. Work in the issue tracker is dominated by enhancement requests, bug reports, and user questions.